Doctors are drowning in data they cannot easily combine—genomic sequences, medical images, blood tests, and lifestyle records all sit in separate systems with incompatible formats. This project builds software tools to stitch those data types together securely, so artificial intelligence can spot patterns that predict heart attacks or guide treatment before symptoms appear. Current methods for integrating genomic data with other health information are slow, fragmented, and often violate privacy rules when shared across borders. The researchers will create portable analysis tools that work across hospitals without moving sensitive patient data, extend existing federated learning systems to handle genomic computations, and improve how clinicians prioritise disease-causing genetic variants. They will also test these tools in five real-world clinical sites across Europe. If successful, the tools could make personalised cardiovascular medicine routine rather than exceptional. A patient’s genome, scan results, and wearable-device data could feed into a single model that recommends the right drug at the right dose, reducing trial-and-error prescribing. The project also aligns with Europe’s “1+ Million Genomes” initiative, meaning the infrastructure could scale to national health systems without compromising data security.
View original technical description
Healthcare is the fasted growing EU27 expenditure. Personalised medicine, comprising tailored approaches for prevention, diagnosis, monitoring and treatment is essential to reduce the burden of disease and improve the quality of life. Integration of multiple data types (multimodal data) into artificial intelligence models is required for the development of accurate and personalised interventions. This is particularly true for the inclusion of genomic data, which is information-rich and individual-specific, and more routinely available as the cost of sequencing continues to fall. Multimodal data integration is complex due to privacy & governance requirements, the presence of multiple standards, distinct data formats, and underlying data complexity and volume. NextGen tools will remove barriers in data integration several cardiovascular use cases. NextGen deliverables will include tooling for multimodal data integration and research portability, extension of secure federated analytics to genomic computation, more effective federated learning over distributed infrastructures, more effective and accessible tools for genomic data analysis; improved clinical efficiency of variant prioritisation; scalable genomic data curation; and improved data discoverability and data management. A comprehensive gap analysis of the existing landscape, factoring ongoing initiatives will ensure NextGen deliverables are forward-looking and complementary. NextGen embedded governance framework and robust regulatory processes will ensure secure multi-jurisdictional multiomic multimodal data access aligned with initiatives including “1+ Million Genomes” and the European Health Data Space. Several real-world pilots will demonstrate the effectiveness of NextGen tools and will be integrated in the NextGen Pathfinder network of five collaborating clinical sites as a selfcontained data ecosystem and comprehensive proof of concept.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know